YOUR READING STUDIO

Free text to speech.
Right on your device.

Free speech, on your own device. Download a voice model once, bring your words, and listen at your own pace.

01 / THE WORDS

What shall we read?

02 / THE VOICE

Make it yours.

Checking…

Choose a model to prepare local speech.

Checking model availability…

Supertonic is the default. Its first download is about 263 MB plus voices, saved in this browser on your device for later visits.

Device & storage Settings

Speed depends on your device. If GPU loading fails, we try the CPU. Only one model is loaded at a time.

Models are stored in this website’s browser storage. Each visitor downloads their own copy. Clearing this site’s data removes that copy.

Add a Hugging Face model Advanced

Use a compatible ONNX repository. Safetensors and GGUF need different engines.

1.0×
0.5×2.0×

Your text and audio stay in this browser. No account or API key.

03 / THE LISTENING

Take a moment.

Your reading will appear here.